stuff

.gitignore

@@ -1,3 +1,5 @@
 .DS_Store
 node_modules/*
-yarn.lock
+yarn.lock
+tesseract.dev.js
+worker.dev.js

README.md

@@ -34,12 +34,11 @@ Or you can grab copies of `tesseract.js` and `worker.js` from the [dist folder](
 ```html
 <script src='/path/to/tesseract.js'></script>
 <script>
-var LocalTesseract = Tesseract.create({
+window.Tesseract = Tesseract.create({
     workerPath: '/path/to/worker.js',
     langPath: 'https://cdn.rawgit.com/naptha/tessdata/gh-pages/3.02/',
     tesseractPath: 'https://cdn.rawgit.com/naptha/tesseract.js-core/0.1.0/index.js',
 })
-// from now on use LocalTesseract instead of Tesseract
 </script>
 ```
 
@@ -156,8 +155,8 @@ In NodeJS, an image can be
 
 
 ## TesseractJob
-A TesseractJob is an an object returned by a call to recognize or detect.
-All methods of a given TesseractJob return that TesseractJob to enable chaining. 
+
+A TesseractJob is an an object returned by a call to `recognize` or `detect`. It's inspired by the ES6 Promise interface and provides `then` and `catch` methods. One important difference is that these methods return the job itself (to enable chaining) rather than new. 
 
 Typical use is: 
 ```javascript

dist/tesseract.js

@@ -1,5 +1,273 @@
 (function(f){if(typeof exports==="object"&&typeof module!=="undefined"){module.exports=f()}else if(typeof define==="function"&&define.amd){define([],f)}else{var g;if(typeof window!=="undefined"){g=window}else if(typeof global!=="undefined"){g=global}else if(typeof self!=="undefined"){g=self}else{g=this}g.Tesseract = f()}})(function(){var define,module,exports;return (function e(t,n,r){function s(o,u){if(!n[o]){if(!t[o]){var a=typeof require=="function"&&require;if(!u&&a)return a(o,!0);if(i)return i(o,!0);var f=new Error("Cannot find module '"+o+"'");throw f.code="MODULE_NOT_FOUND",f}var l=n[o]={exports:{}};t[o][0].call(l.exports,function(e){var n=t[o][1][e];return s(n?n:e)},l,l.exports,e,t,n,r)}return n[o].exports}var i=typeof require=="function"&&require;for(var o=0;o<r.length;o++)s(r[o]);return s})({1:[function(require,module,exports){
 'use strict';
+/* eslint-disable no-unused-vars */
+var hasOwnProperty = Object.prototype.hasOwnProperty;
+var propIsEnumerable = Object.prototype.propertyIsEnumerable;
+
+function toObject(val) {
+	if (val === null || val === undefined) {
+		throw new TypeError('Object.assign cannot be called with null or undefined');
+	}
+
+	return Object(val);
+}
+
+function shouldUseNative() {
+	try {
+		if (!Object.assign) {
+			return false;
+		}
+
+		// Detect buggy property enumeration order in older V8 versions.
+
+		// https://bugs.chromium.org/p/v8/issues/detail?id=4118
+		var test1 = new String('abc');  // eslint-disable-line
+		test1[5] = 'de';
+		if (Object.getOwnPropertyNames(test1)[0] === '5') {
+			return false;
+		}
+
+		// https://bugs.chromium.org/p/v8/issues/detail?id=3056
+		var test2 = {};
+		for (var i = 0; i < 10; i++) {
+			test2['_' + String.fromCharCode(i)] = i;
+		}
+		var order2 = Object.getOwnPropertyNames(test2).map(function (n) {
+			return test2[n];
+		});
+		if (order2.join('') !== '0123456789') {
+			return false;
+		}
+
+		// https://bugs.chromium.org/p/v8/issues/detail?id=3056
+		var test3 = {};
+		'abcdefghijklmnopqrst'.split('').forEach(function (letter) {
+			test3[letter] = letter;
+		});
+		if (Object.keys(Object.assign({}, test3)).join('') !==
+				'abcdefghijklmnopqrst') {
+			return false;
+		}
+
+		return true;
+	} catch (e) {
+		// We don't expect any of the above to throw, but better to be safe.
+		return false;
+	}
+}
+
+module.exports = shouldUseNative() ? Object.assign : function (target, source) {
+	var from;
+	var to = toObject(target);
+	var symbols;
+
+	for (var s = 1; s < arguments.length; s++) {
+		from = Object(arguments[s]);
+
+		for (var key in from) {
+			if (hasOwnProperty.call(from, key)) {
+				to[key] = from[key];
+			}
+		}
+
+		if (Object.getOwnPropertySymbols) {
+			symbols = Object.getOwnPropertySymbols(from);
+			for (var i = 0; i < symbols.length; i++) {
+				if (propIsEnumerable.call(from, symbols[i])) {
+					to[symbols[i]] = from[symbols[i]];
+				}
+			}
+		}
+	}
+
+	return to;
+};
+
+},{}],2:[function(require,module,exports){
+// shim for using process in browser
+var process = module.exports = {};
+
+// cached from whatever global is present so that test runners that stub it
+// don't break things.  But we need to wrap it in a try catch in case it is
+// wrapped in strict mode code which doesn't define any globals.  It's inside a
+// function because try/catches deoptimize in certain engines.
+
+var cachedSetTimeout;
+var cachedClearTimeout;
+
+function defaultSetTimout() {
+    throw new Error('setTimeout has not been defined');
+}
+function defaultClearTimeout () {
+    throw new Error('clearTimeout has not been defined');
+}
+(function () {
+    try {
+        if (typeof setTimeout === 'function') {
+            cachedSetTimeout = setTimeout;
+        } else {
+            cachedSetTimeout = defaultSetTimout;
+        }
+    } catch (e) {
+        cachedSetTimeout = defaultSetTimout;
+    }
+    try {
+        if (typeof clearTimeout === 'function') {
+            cachedClearTimeout = clearTimeout;
+        } else {
+            cachedClearTimeout = defaultClearTimeout;
+        }
+    } catch (e) {
+        cachedClearTimeout = defaultClearTimeout;
+    }
+} ())
+function runTimeout(fun) {
+    if (cachedSetTimeout === setTimeout) {
+        //normal enviroments in sane situations
+        return setTimeout(fun, 0);
+    }
+    // if setTimeout wasn't available but was latter defined
+    if ((cachedSetTimeout === defaultSetTimout || !cachedSetTimeout) && setTimeout) {
+        cachedSetTimeout = setTimeout;
+        return setTimeout(fun, 0);
+    }
+    try {
+        // when when somebody has screwed with setTimeout but no I.E. maddness
+        return cachedSetTimeout(fun, 0);
+    } catch(e){
+        try {
+            // When we are in I.E. but the script has been evaled so I.E. doesn't trust the global object when called normally
+            return cachedSetTimeout.call(null, fun, 0);
+        } catch(e){
+            // same as above but when it's a version of I.E. that must have the global object for 'this', hopfully our context correct otherwise it will throw a global error
+            return cachedSetTimeout.call(this, fun, 0);
+        }
+    }
+
+
+}
+function runClearTimeout(marker) {
+    if (cachedClearTimeout === clearTimeout) {
+        //normal enviroments in sane situations
+        return clearTimeout(marker);
+    }
+    // if clearTimeout wasn't available but was latter defined
+    if ((cachedClearTimeout === defaultClearTimeout || !cachedClearTimeout) && clearTimeout) {
+        cachedClearTimeout = clearTimeout;
+        return clearTimeout(marker);
+    }
+    try {
+        // when when somebody has screwed with setTimeout but no I.E. maddness
+        return cachedClearTimeout(marker);
+    } catch (e){
+        try {
+            // When we are in I.E. but the script has been evaled so I.E. doesn't  trust the global object when called normally
+            return cachedClearTimeout.call(null, marker);
+        } catch (e){
+            // same as above but when it's a version of I.E. that must have the global object for 'this', hopfully our context correct otherwise it will throw a global error.
+            // Some versions of I.E. have different rules for clearTimeout vs setTimeout
+            return cachedClearTimeout.call(this, marker);
+        }
+    }
+
+
+
+}
+var queue = [];
+var draining = false;
+var currentQueue;
+var queueIndex = -1;
+
+function cleanUpNextTick() {
+    if (!draining || !currentQueue) {
+        return;
+    }
+    draining = false;
+    if (currentQueue.length) {
+        queue = currentQueue.concat(queue);
+    } else {
+        queueIndex = -1;
+    }
+    if (queue.length) {
+        drainQueue();
+    }
+}
+
+function drainQueue() {
+    if (draining) {
+        return;
+    }
+    var timeout = runTimeout(cleanUpNextTick);
+    draining = true;
+
+    var len = queue.length;
+    while(len) {
+        currentQueue = queue;
+        queue = [];
+        while (++queueIndex < len) {
+            if (currentQueue) {
+                currentQueue[queueIndex].run();
+            }
+        }
+        queueIndex = -1;
+        len = queue.length;
+    }
+    currentQueue = null;
+    draining = false;
+    runClearTimeout(timeout);
+}
+
+process.nextTick = function (fun) {
+    var args = new Array(arguments.length - 1);
+    if (arguments.length > 1) {
+        for (var i = 1; i < arguments.length; i++) {
+            args[i - 1] = arguments[i];
+        }
+    }
+    queue.push(new Item(fun, args));
+    if (queue.length === 1 && !draining) {
+        runTimeout(drainQueue);
+    }
+};
+
+// v8 likes predictible objects
+function Item(fun, array) {
+    this.fun = fun;
+    this.array = array;
+}
+Item.prototype.run = function () {
+    this.fun.apply(null, this.array);
+};
+process.title = 'browser';
+process.browser = true;
+process.env = {};
+process.argv = [];
+process.version = ''; // empty string to avoid regexp issues
+process.versions = {};
+
+function noop() {}
+
+process.on = noop;
+process.addListener = noop;
+process.once = noop;
+process.off = noop;
+process.removeListener = noop;
+process.removeAllListeners = noop;
+process.emit = noop;
+
+process.binding = function (name) {
+    throw new Error('process.binding is not supported');
+};
+
+process.cwd = function () { return '/' };
+process.chdir = function (dir) {
+    throw new Error('process.chdir is not supported');
+};
+process.umask = function() { return 0; };
+
+},{}],3:[function(require,module,exports){
+(function (process){
+'use strict';
 
 var defaultOptions = {
     workerPath: 'https://cdn.rawgit.com/naptha/tesseract.js/0.1.3/dist/worker.js',
@@ -7,9 +275,9 @@ var defaultOptions = {
     langPath: 'https://cdn.rawgit.com/naptha/tessdata/gh-pages/3.02/'
 };
 
-if (location.hostname === '127.0.0.1' && location.port == '7355') {
+if (process.env.NODE_ENV === "development") {
     console.debug('Using Development Configuration');
-    defaultOptions.workerPath = location.protocol + '//' + location.host + '/dist/worker.js';
+    defaultOptions.workerPath = location.protocol + '//' + location.host + '/dist/worker.dev.js';
 }
 
 exports.defaultOptions = defaultOptions;
@@ -45,14 +313,23 @@ function loadImage(image, cb) {
         if (/^\#/.test(image)) {
             // element css selector
             return loadImage(document.querySelector(image), cb);
-        } else {
-            // url or path
+        } else if (/(blob|data)\:/.test(image)) {
+            // data url
             var im = new Image();
             im.src = image;
             im.onload = function (e) {
                 return loadImage(im, cb);
             };
             return;
+        } else {
+            var xhr = new XMLHttpRequest();
+            xhr.open('GET', image, true);
+            xhr.responseType = "blob";
+            xhr.onload = function (e) {
+                return loadImage(xhr.response, cb);
+            };
+            xhr.send(null);
+            return;
         }
     } else if (image instanceof File) {
         // files
@@ -79,11 +356,14 @@ function loadImage(image, cb) {
         // canvas context
         var data = image.getImageData(0, 0, image.canvas.width, image.canvas.height);
         return loadImage(data, cb);
+    } else {
+        return cb(image);
     }
-    cb(image);
+    throw new Error('Missing return in loadImage cascade');
 }
 
-},{}],2:[function(require,module,exports){
+}).call(this,require('_process'))
+},{"_process":2}],4:[function(require,module,exports){
 "use strict";
 
 // The result of dump.js is a big JSON tree
@@ -150,8 +430,8 @@ module.exports = function circularize(page) {
     return page;
 };
 
-},{}],3:[function(require,module,exports){
-"use strict";
+},{}],5:[function(require,module,exports){
+'use strict';
 
 var _createClass = function () { function defineProperties(target, props) { for (var i = 0; i < props.length; i++) { var descriptor = props[i]; descriptor.enumerable = descriptor.enumerable || false; descriptor.configurable = true; if ("value" in descriptor) descriptor.writable = true; Object.defineProperty(target, descriptor.key, descriptor); } } return function (Constructor, protoProps, staticProps) { if (protoProps) defineProperties(Constructor.prototype, protoProps); if (staticProps) defineProperties(Constructor, staticProps); return Constructor; }; }();
 
@@ -159,9 +439,13 @@ function _classCallCheck(instance, Constructor) { if (!(instance instanceof Cons
 
 var adapter = require('./node/index.js');
 var circularize = require('./common/circularize.js');
+var objectAssign = require('object-assign');
 
 function create(workerOptions) {
-	return new TesseractWorker(workerOptions);
+	workerOptions = workerOptions || {};
+	var worker = new TesseractWorker(objectAssign({}, adapter.defaultOptions, workerOptions));
+	worker.create = create;
+	return worker;
 }
 
 var TesseractWorker = function () {
@@ -334,10 +618,9 @@ var TesseractJob = function () {
 	return TesseractJob;
 }();
 
-var DefaultTesseract = create(adapter.defaultOptions);
-DefaultTesseract.create = create;
+var DefaultTesseract = create();
 
 module.exports = DefaultTesseract;
 
-},{"./common/circularize.js":2,"./node/index.js":1}]},{},[3])(3)
+},{"./common/circularize.js":4,"./node/index.js":3,"object-assign":1}]},{},[5])(5)
 });

dist/worker.js

@@ -11925,11 +11925,15 @@ function fetchLanguageData(req, res, cb) {
 }
 
 },{"../common/langdata.json":46,"level-js":12,"pako":21}],43:[function(require,module,exports){
-(function (global){
-"use strict";
+(function (process,global){
+'use strict';
 
 var workerUtils = require('../common/worker.js');
 
+if (process.env.NODE_ENV === "development") {
+    console.debug('Using Development Worker');
+}
+
 global.addEventListener('message', function (e) {
     var packet = e.data;
     workerUtils.dispatchHandlers(packet, function (obj) {
@@ -11950,8 +11954,8 @@ exports.getLanguageData = require('./lang.js');
 
 workerUtils.setAdapter(module.exports);
 
-}).call(this,typeof global !== "undefined" ? global : typeof self !== "undefined" ? self : typeof window !== "undefined" ? window : {})
-},{"../common/worker.js":47,"./lang.js":42}],44:[function(require,module,exports){
+}).call(this,require('_process'),typeof global !== "undefined" ? global : typeof self !== "undefined" ? self : typeof window !== "undefined" ? window : {})
+},{"../common/worker.js":47,"./lang.js":42,"_process":37}],44:[function(require,module,exports){
 'use strict';
 
 // This converts an image to grayscale

examples/file-input/demo.html

@@ -1,2 +1,2 @@
-<script src="/dist/tesseract.js"></script>
+<script src="/dist/tesseract.dev.js"></script>
 <input type="file" onchange="Tesseract.recognize(this.files[0]).progress(console.log)">

package.json

@@ -5,7 +5,7 @@
   "main": "src/index.js",
   "scripts": {
     "test": "echo \"Error: no test specified\" & exit 1",
-    "start": "watchify src/index.js  -t [ babelify --presets [ es2015 ] ] -o dist/tesseract.js --standalone Tesseract & watchify src/browser/worker.js  -t [ babelify --presets [ es2015 ] ] -o dist/worker.js & http-server -p 7355",
+    "start": "watchify src/index.js  -t [ envify --NODE_ENV development ] -t [ babelify --presets [ es2015 ] ] -o dist/tesseract.dev.js --standalone Tesseract & watchify src/browser/worker.js  -t [ envify --NODE_ENV development ] -t [ babelify --presets [ es2015 ] ] -o dist/worker.dev.js & http-server -p 7355",
     "build": "browserify src/index.js -t [ babelify --presets [ es2015 ] ] -o dist/tesseract.js --standalone Tesseract && browserify src/browser/worker.js -t [ babelify --presets [ es2015 ] ] -o dist/worker.js"
   },
   "browser": {
@@ -17,6 +17,7 @@
     "babel-preset-es2015": "^6.16.0",
     "babelify": "^7.3.0",
     "browserify": "^13.1.0",
+    "envify": "^3.4.1",
     "http-server": "^0.9.0",
     "watchify": "^3.7.0"
   },
@@ -24,6 +25,7 @@
     "file-type": "^3.8.0",
     "jpeg-js": "^0.2.0",
     "level-js": "^2.2.4",
+    "object-assign": "^4.1.0",
     "pako": "^1.0.3",
     "png.js": "^0.2.1",
     "tesseract.js-core": "^1.0.2"

src/browser/index.js

@@ -4,16 +4,15 @@ var defaultOptions = {
     langPath: 'https://cdn.rawgit.com/naptha/tessdata/gh-pages/3.02/',
 }
 
-if(location.hostname === '127.0.0.1' && location.port == '7355'){
+if (process.env.NODE_ENV === "development") {
     console.debug('Using Development Configuration')
-    defaultOptions.workerPath = location.protocol + '//' + location.host + '/dist/worker.js'
+    defaultOptions.workerPath = location.protocol + '//' + location.host + '/dist/worker.dev.js'
 }
 
 
 exports.defaultOptions = defaultOptions;
 
 
-
 exports.spawnWorker = function spawnWorker(instance, workerOptions){
     if(window.Blob && window.URL){
         var blob = new Blob(['importScripts("' + workerOptions.workerPath + '");'])
@@ -46,12 +45,19 @@ function loadImage(image, cb){
         if(/^\#/.test(image)){
             // element css selector
             return loadImage(document.querySelector(image), cb)
-        }else{
-            // url or path
+        }else if(/(blob|data)\:/.test(image)){
+            // data url
             var im = new Image
             im.src = image;
             im.onload = e => loadImage(im, cb);
             return
+        }else{
+            var xhr = new XMLHttpRequest();
+            xhr.open('GET', image, true)
+            xhr.responseType = "blob";
+            xhr.onload = e => loadImage(xhr.response, cb);
+            xhr.send(null)
+            return
         }
     }else if(image instanceof File){
         // files
@@ -76,6 +82,9 @@ function loadImage(image, cb){
         // canvas context
         var data = image.getImageData(0, 0, image.canvas.width, image.canvas.height);
         return loadImage(data, cb)
+    }else{
+        return cb(image)
     }
-    cb(image)
+    throw new Error('Missing return in loadImage cascade')
+
 }

src/browser/lang.js

@@ -1,4 +1,4 @@
-var leveljs = require('level-js')
+const leveljs = require('level-js')
 var db = typeof indexedDB === 'undefined' ? { open: (_, cb) =>  cb(true) } : leveljs('./tessdata2')
 
 var langdata = require('../common/langdata.json')
@@ -22,7 +22,7 @@ module.exports = function getLanguageData(req, res, cb){
 }
 
 
-var ungzip = require('pako').ungzip;
+const ungzip = require('pako').ungzip;
 
 function fetchLanguageData(req, res, cb){
     var lang = req.options.lang;

src/browser/worker.js

@@ -1,6 +1,8 @@
-"use strict";
+const workerUtils = require('../common/worker.js')
 
-var workerUtils = require('../common/worker.js')
+if (process.env.NODE_ENV === "development") {
+    console.debug('Using Development Worker')
+}
 
 global.addEventListener('message', function(e){
     var packet = e.data;

src/index.js

@@ -1,11 +1,12 @@
-"use strict";
-
-var adapter = require('./node/index.js')
-var circularize = require('./common/circularize.js')
-
+const adapter = require('./node/index.js')
+const circularize = require('./common/circularize.js')
+const objectAssign = require('object-assign');
 
 function create(workerOptions){
-	return new TesseractWorker(workerOptions)
+	workerOptions = workerOptions || {};
+	var worker = new TesseractWorker(objectAssign({}, adapter.defaultOptions, workerOptions))
+	worker.create = create;
+	return worker;
 }
 
 class TesseractWorker {
@@ -142,8 +143,7 @@ class TesseractJob {
 }
 
 
-var DefaultTesseract = create(adapter.defaultOptions)
-DefaultTesseract.create = create;
+var DefaultTesseract = create()
 
 module.exports = DefaultTesseract
 

src/node/index.js

@@ -1,12 +1,12 @@
-var path = require('path')
+const path = require('path')
 
 exports.defaultOptions = {
     workerPath: path.join(__dirname, 'worker.js'),
     langPath: 'http://cdn.rawgit.com/naptha/tessdata/gh-pages/3.02/',
 }
 
-var fork = require('child_process').fork;
-var fs = require('fs')
+const fork = require('child_process').fork;
+const fs = require('fs')
 
 exports.spawnWorker = function spawnWorker(instance, workerOptions){
     var cp = fork(workerOptions.workerPath);
@@ -39,7 +39,6 @@ function loadImage(image, cb){
         var fileType = require('file-type');
         var mime = fileType(image).mime
 
-
         if(mime === 'image/png'){
             var PNGReader = require('png.js');
             var reader = new PNGReader(image);

src/node/lang.js

@@ -1,7 +1,7 @@
-var http = require("http"),
-    zlib = require("zlib"),
-    fs   = require("fs"),
-    path = require("path");
+const http = require("http"),
+      zlib = require("zlib"),
+      fs   = require("fs"),
+      path = require("path");
 
 var langdata = require('../common/langdata.json')
 

src/node/worker.js

@@ -1,6 +1,4 @@
-"use strict";
-
-var workerUtils = require('../common/worker.js')
+const workerUtils = require('../common/worker.js')
 
 process.on('message', function(packet){
     workerUtils.dispatchHandlers(packet, obj => process.send(obj))